您好，欢迎访问中国农业科学院 机构知识库！

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

LAND SURFACE EMISSIVITY ESTIMATION FROM SATELLITE DATA WITH MACHINE LEARNING

文献类型： 会议论文

第一作者： Zhao-Liang Li

作者： Zhao-Liang Li 1 ; Yong-Gang Qian 2 ; Si-Bo Duan 1 ; Xiu-Juan Li 3 ; Hua Wu 3 ;

作者机构： 1.Key Laboratory of Agri-informatics, Ministry of Agriculture/Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences

2.Aerospace Information Research Institute, Chinese Academy of Sciences

3.State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences

关键词： Reflectivity;Gradient boost regression tree;Land surface emissivity;Retrieval

会议名称： IEEE International Geoscience and Remote Sensing Symposium

主办单位：

页码： 3737-3740

摘要： Land Surface Emissivity (LSE) is an important parameter in thermal infrared remote sensing, which is of great significance to temperature inversion. In this study, the Gradient Boost Regression Tree (GBRT) was proposed to directly retrieve LSEs of MODIS thermal infrared channels 29 (8.4-8.7 μm), 31 (10.78-11.28 μm), and 32 (11.77-12.27 μm) from the visible and near infrared (VNIR) data. We selected the variables related with LSE, including reflectivity, view zenith, solar zenith, land surface type, vegetation index (EVI), Normalized Difference Water Index (NDWI) and Leaf Area Index (LAI). The results of the test set showed that RMSEs of the estimated LSEs were 0.013 in channel 29, 0.005 in 31 and 0.004 in 32, which were more accurate than existing methods. Eight regions with different ground features were also selected to further evaluate the applicability of the model. In most areas, the RMSEs were below 0.015 in channel 29, below 0.005 in channel 31 and 32. In addition, the spatial distributions of the estimated LSEs and those extracted from MYD11B1 and MYD21A1D in H19V08 were compared, which were also reasonable. In general, it is feasible to use the selected variables with the GBRT model to directly retrieve the LSEs.

分类号： tp7-53

  • 相关文献

[1]An Algorithm for Retrieving Land Surface Temperatures Using VIIRS Data in Combination with Multi-Sensors. Xia, Lang,Mao, Kebiao,Ma, Ying,Zhao, Fen,Qin, Zhihao,Jiang, Lipeng,Shen, Xinyi. 2014

[2]Estimating the crop leaf area index using hyperspectral remote sensing. Liu Ke,Zhou Qing-bo,Wu Wen-bin,Tang Hua-jun,Liu Ke,Zhou Qing-bo,Wu Wen-bin,Tang Hua-jun,Wu Wen-bin,Xia Tian.

[3]A PHYSICAL METHOD FOR RETRIEVING MICROWAVE LAND SURFACE EMISSIVITY UNDER ALL-WEATHER CONDITIONS. Fang-Cheng Zhou,Shihao Tang,Hua Wu,Zhao-Liang Li,Xiaoning Song,Xiuzhen Han,Shengli Wu. 2019

[4]AN ALGORITHM FOR RETRIEVING LAND SURFACE TEMPERATURE FROM AMSR-E DATA OVER THE DESERT REGIONS. Rong-Lin Tang,Xiaoning Song,Guangjian Yan,Si-Bo Duan,Fang-Cheng Zhou,Zhao-Liang Li,Hua Wu,Bo-Hui Tang. 2017

[5]A Combining Method for Generating Land Surface Temperature with High Spatiotemporal Resolution. Yitao Li,Hua Wu,Zhao-Liang Li,Caixia Gao. 2022

作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：中国农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台